def infer():
# Config Loader
test_args = ConfigSection()
ConfigLoader().load_config(cfgfile, {"POS_test": test_args})
# fetch dictionary size and number of labels from pickle files
word2index = load_pickle(pickle_path, "word2id.pkl")
test_args["vocab_size"] = len(word2index)
index2label = load_pickle(pickle_path, "label2id.pkl")
test_args["num_classes"] = len(index2label)
# Define the same model
model = AdvSeqLabel(test_args)
try:
ModelLoader.load_pytorch(model, "./save/trained_model.pkl")
print('model loaded!')
except Exception as e:
print('cannot load model!')
raise
# Data Loader
infer_data = SeqLabelDataSet(load_func=BaseLoader.load_lines)
infer_data.load(data_infer_path, vocabs={"word_vocab": word2index}, infer=True)
print('data loaded')
# Inference interface
infer = SeqLabelInfer(pickle_path)
results = infer.predict(model, infer_data)
print(results)
print("Inference finished!")
def predict():
# Config Loader
test_args = ConfigSection()
ConfigLoader().load_config(cfgfile, {"POS_test": test_args})
# fetch dictionary size and number of labels from pickle files
word2index = load_pickle(pickle_path, "word2id.pkl")
test_args["vocab_size"] = len(word2index)
index2label = load_pickle(pickle_path, "label2id.pkl")
test_args["num_classes"] = len(index2label)
# load dev data
dev_data = load_pickle(pickle_path, "data_dev.pkl")
# Define the same model
model = AdvSeqLabel(test_args)
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, "./save/trained_model.pkl")
print("model loaded!")
# Tester
test_args["evaluator"] = SeqLabelEvaluator()
tester = SeqLabelTester(**test_args.data)
# Start testing
tester.test(model, dev_data)
def _get_section(self, sect_name):
"""This is the function to get the section with the section name.
:param sect_name: The name of section what wants to load.
:return: The section.
"""
sect = ConfigSection()
ConfigLoader().load_config(self.file_path, {sect_name: sect})
return sect
def train():
# Config Loader
train_args = ConfigSection()
test_args = ConfigSection()
ConfigLoader().load_config(cfgfile, {"train": train_args, "test": test_args})
print("loading data set...")
data = SeqLabelDataSet(load_func=TokenizeDataSetLoader.load)
data.load(cws_data_path)
data_train, data_dev = data.split(ratio=0.3)
train_args["vocab_size"] = len(data.word_vocab)
train_args["num_classes"] = len(data.label_vocab)
print("vocab size={}, num_classes={}".format(len(data.word_vocab), len(data.label_vocab)))
change_field_is_target(data_dev, "truth", True)
save_pickle(data_dev, "./save/", "data_dev.pkl")
save_pickle(data.word_vocab, "./save/", "word2id.pkl")
save_pickle(data.label_vocab, "./save/", "label2id.pkl")
# Trainer
trainer = SeqLabelTrainer(epochs=train_args["epochs"], batch_size=train_args["batch_size"],
validate=train_args["validate"],
use_cuda=train_args["use_cuda"], pickle_path=train_args["pickle_path"],
save_best_dev=True, print_every_step=10, model_name="trained_model.pkl",
evaluator=SeqLabelEvaluator())
# Model
model = AdvSeqLabel(train_args)
try:
ModelLoader.load_pytorch(model, "./save/saved_model.pkl")
print('model parameter loaded!')
except Exception as e:
print("No saved model. Continue.")
pass
# Start training
trainer.train(model, data_train, data_dev)
print("Training finished!")
# Saver
saver = ModelSaver("./save/trained_model.pkl")
saver.save_pytorch(model)
print("Model saved!")
def test_case_2(self):
config = "[section_A]\n[section_B]\n"
with open("./test.cfg", "w", encoding="utf-8") as f:
f.write(config)
saver = ConfigSaver("./test.cfg")
section = ConfigSection()
section["doubles"] = 0.8
section["tt"] = [1, 2, 3]
section["test"] = 105
section["str"] = "this is a str"
saver.save_config_file("section_A", section)
os.system("rm ./test.cfg")
def _load_all(src):
model_path = src
src = os.path.dirname(src)
word_v = _load(src + '/word_v.pkl')
pos_v = _load(src + '/pos_v.pkl')
tag_v = _load(src + '/tag_v.pkl')
pos_pp = torch.load(src + '/pos_pp.pkl')['pipeline']
model_args = ConfigSection()
ConfigLoader.load_config('cfg.cfg', {'model': model_args})
model_args['word_vocab_size'] = len(word_v)
model_args['pos_vocab_size'] = len(pos_v)
model_args['num_label'] = len(tag_v)
model = BiaffineParser(**model_args.data)
model.load_state_dict(torch.load(model_path))
return {
'word_v': word_v,
'pos_v': pos_v,
'tag_v': tag_v,
'model': model,
'pos_pp': pos_pp,
}
def test_case_1(self):
config_file_dir = "test/io/"
config_file_name = "config"
config_file_path = os.path.join(config_file_dir, config_file_name)
tmp_config_file_path = os.path.join(config_file_dir, "tmp_config")
with open(config_file_path, "r") as f:
lines = f.readlines()
standard_section = ConfigSection()
t_section = ConfigSection()
ConfigLoader().load_config(config_file_path, {
"test": standard_section,
"t": t_section
})
config_saver = ConfigSaver(config_file_path)
section = ConfigSection()
section["doubles"] = 0.8
section["tt"] = 0.5
section["test"] = 105
section["str"] = "this is a str"
test_case_2_section = section
test_case_2_section["double"] = 0.5
for k in section.__dict__.keys():
standard_section[k] = section[k]
config_saver.save_config_file("test", section)
config_saver.save_config_file("another-test", section)
config_saver.save_config_file("one-another-test", section)
config_saver.save_config_file("test-case-2", section)
test_section = ConfigSection()
at_section = ConfigSection()
another_test_section = ConfigSection()
one_another_test_section = ConfigSection()
a_test_case_2_section = ConfigSection()
ConfigLoader().load_config(
config_file_path, {
"test": test_section,
"another-test": another_test_section,
"t": at_section,
"one-another-test": one_another_test_section,
"test-case-2": a_test_case_2_section
})
assert test_section == standard_section
assert at_section == t_section
assert another_test_section == section
assert one_another_test_section == section
assert a_test_case_2_section == test_case_2_section
config_saver.save_config_file("test", section)
with open(config_file_path, "w") as f:
f.writelines(lines)
with open(tmp_config_file_path, "w") as f:
f.write('[test]\n')
f.write('this is an fault example\n')
tmp_config_saver = ConfigSaver(tmp_config_file_path)
try:
tmp_config_saver._read_section()
except Exception as e:
pass
os.remove(tmp_config_file_path)
try:
tmp_config_saver = ConfigSaver("file-NOT-exist")
except Exception as e:
pass
# emb_file_name = '/home/yfshao/glove.6B.100d.txt'
# loader = ConlluDataLoader()
datadir = '/home/yfshao/workdir/parser-data/'
train_data_name = "train_ctb5.txt"
dev_data_name = "dev_ctb5.txt"
test_data_name = "test_ctb5.txt"
emb_file_name = "/home/yfshao/workdir/parser-data/word_OOVthr_30_100v.txt"
# emb_file_name = "/home/yfshao/workdir/word_vector/cc.zh.300.vec"
loader = CTBDataLoader()
cfgfile = './cfg.cfg'
processed_datadir = './save'
# Config Loader
train_args = ConfigSection()
test_args = ConfigSection()
model_args = ConfigSection()
optim_args = ConfigSection()
ConfigLoader.load_config(
cfgfile, {
"train": train_args,
"test": test_args,
"model": model_args,
"optim": optim_args
})
print('trainre Args:', train_args.data)
print('test Args:', test_args.data)
print('optim Args:', optim_args.data)
dim=attention_unit,
num_vec=attention_hops)
self.mlp = MLP(
size_layer=[lstm_hidden_size * 2 * attention_hops, nfc, class_num])
def forward(self, x):
x_emb = self.embedding(x)
output = self.lstm(x_emb)
after_attention, penalty = self.attention(output, x)
after_attention = after_attention.view(after_attention.size(0), -1)
output = self.mlp(after_attention)
return output
def loss(self, predict, ground_truth):
print("predict:%s; g:%s" %
(str(predict.size()), str(ground_truth.size())))
print(ground_truth)
return F.cross_entropy(predict, ground_truth)
train_args = ConfigSection()
ConfigLoader("good path").load_config('config.cfg', {"train": train_args})
train_args['vocab'] = len(word2index)
trainer = ClassificationTrainer(**train_args.data)
# for k in train_args.__dict__.keys():
# print(k, train_args[k])
model = SELF_ATTENTION_YELP_CLASSIFICATION(train_args)
trainer.train(model, train_data, dev_data)